Related Experiment Video
Updated: Aug 21, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.3K
Calibrated bagging deep learning for image semantic segmentation: A case study on COVID-19 chest X-ray image
Lucy Nwosu1, Xiangfang Li1,2, Lijun Qian1,2
1Center of Computational Systems Biology (CCSB), Department of Electrical and Computer Engineering, Prairie View A&M University, Texas A&M University System, Prairie View, Texas, United States of America.
Plos One
|November 16, 2022
Summary
This study introduces an ensemble deep learning model to improve COVID-19 detection from chest X-rays. The new method enhances image segmentation and reduces prediction uncertainty for more reliable diagnoses.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Deep Learning
Background:
- Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19).
- Chest X-ray (CXR) and computed tomography (CT) are vital for COVID-19 diagnosis.
- Deep learning (AI) models analyze medical images for segmentation and classification, but their prediction uncertainty is understudied.
Purpose of the Study:
- To develop a novel ensemble deep learning model.
- To enhance segmentation performance in medical image analysis.
- To reduce prediction uncertainty in AI models for COVID-19 diagnosis.
Main Methods:
- An ensemble deep learning model was developed by integrating bagging deep learning.
- Model calibration techniques were incorporated to address prediction uncertainty.
- The method was validated using a large dataset of CXR images for segmentation tasks.
Main Results:
- The proposed ensemble model demonstrated improved segmentation performance.
- A significant decrease in prediction uncertainty was observed.
- The findings suggest enhanced reliability for AI-driven medical image analysis.
Conclusions:
- The novel ensemble deep learning approach effectively improves COVID-19 segmentation on CXR.
- Reducing prediction uncertainty is crucial for safe and reliable AI applications in medical imaging.
- This method offers a promising advancement for AI-assisted diagnosis of infectious diseases.
